quic/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
This toolkit helps machine learning engineers and data scientists make their deep learning models run faster and use less memory, especially on devices like mobile phones or laptops. You provide a trained PyTorch or ONNX model, and it outputs a more efficient, quantized version of that model, ready for deployment. This is for anyone who needs to deploy AI models where computational resources are limited.
2,566 stars. Actively maintained with 71 commits in the last 30 days.
Use this if you need to optimize your trained PyTorch or ONNX neural network models for faster inference and smaller memory footprint on edge devices without significant accuracy loss.
Not ideal if you are working with models that are not based on PyTorch or ONNX, or if your primary goal is to improve model accuracy rather than efficiency.
Stars
2,566
Forks
448
Language
Python
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
71
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/quic/aimet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
InterDigitalInc/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
tensorflow/compression
Data compression in TensorFlow
baler-collaboration/baler
Repository of Baler, a machine learning based data compression tool
thulab/DeepHash
An Open-Source Package for Deep Learning to Hash (DeepHash)
zhanghang1989/PyTorch-Encoding
A CV toolkit for my papers.